1 files changed, 300 insertions, 154 deletions

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 5f7d3db3afd8..d54fa0638dc4 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -12,12 +12,14 @@
 #include <linux/crash_dump.h>
 #include <linux/delay.h>
 #include <linux/efi.h>
+#include <linux/genalloc.h>
 #include <linux/interrupt.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
 #include <linux/irqdomain.h>
 #include <linux/list.h>
 #include <linux/log2.h>
+#include <linux/mem_encrypt.h>
 #include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/msi.h>
@@ -27,6 +29,7 @@
 #include <linux/of_pci.h>
 #include <linux/of_platform.h>
 #include <linux/percpu.h>
+#include <linux/set_memory.h>
 #include <linux/slab.h>
 #include <linux/syscore_ops.h>
 
@@ -38,11 +41,13 @@
 #include <asm/exception.h>
 
 #include "irq-gic-common.h"
+#include <linux/irqchip/irq-msi-lib.h>
 
 #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1ULL << 0)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_22375	(1ULL << 1)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_23144	(1ULL << 2)
 #define ITS_FLAGS_FORCE_NON_SHAREABLE		(1ULL << 3)
+#define ITS_FLAGS_WORKAROUND_HISILICON_162100801	(1ULL << 4)
 
 #define RD_LOCAL_LPI_ENABLED                    BIT(0)
 #define RD_LOCAL_PENDTABLE_PREALLOCATED         BIT(1)
@@ -59,7 +64,8 @@ static u32 lpi_id_bits;
 #define LPI_PROPBASE_SZ		ALIGN(BIT(LPI_NRBITS), SZ_64K)
 #define LPI_PENDBASE_SZ		ALIGN(BIT(LPI_NRBITS) / 8, SZ_64K)
 
-#define LPI_PROP_DEFAULT_PRIO	GICD_INT_DEF_PRI
+static u8 __ro_after_init lpi_prop_prio;
+static struct its_node *find_4_1_its(void);
 
 /*
  * Collection structure - just an ID, and a redistributor address to
@@ -119,6 +125,8 @@ struct its_node {
 	int			vlpi_redist_offset;
 };
 
+static DEFINE_PER_CPU(struct its_node *, local_4_1_its);
+
 #define is_v4(its)		(!!((its)->typer & GITS_TYPER_VLPIS))
 #define is_v4_1(its)		(!!((its)->typer & GITS_TYPER_VMAPP))
 #define device_ids(its)		(FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1)
@@ -163,6 +171,7 @@ struct its_device {
 	struct its_node		*its;
 	struct event_lpi_map	event_map;
 	void			*itt;
+	u32			itt_sz;
 	u32			nr_ites;
 	u32			device_id;
 	bool			shared;
@@ -198,6 +207,89 @@ static DEFINE_IDA(its_vpeid_ida);
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_vlpi_base()	(gic_data_rdist_rd_base() + SZ_128K)
 
+static gfp_t gfp_flags_quirk;
+
+static struct page *its_alloc_pages_node(int node, gfp_t gfp,
+					 unsigned int order)
+{
+	struct page *page;
+	int ret = 0;
+
+	page = alloc_pages_node(node, gfp | gfp_flags_quirk, order);
+
+	if (!page)
+		return NULL;
+
+	ret = set_memory_decrypted((unsigned long)page_address(page),
+				   1 << order);
+	/*
+	 * If set_memory_decrypted() fails then we don't know what state the
+	 * page is in, so we can't free it. Instead we leak it.
+	 * set_memory_decrypted() will already have WARNed.
+	 */
+	if (ret)
+		return NULL;
+
+	return page;
+}
+
+static struct page *its_alloc_pages(gfp_t gfp, unsigned int order)
+{
+	return its_alloc_pages_node(NUMA_NO_NODE, gfp, order);
+}
+
+static void its_free_pages(void *addr, unsigned int order)
+{
+	/*
+	 * If the memory cannot be encrypted again then we must leak the pages.
+	 * set_memory_encrypted() will already have WARNed.
+	 */
+	if (set_memory_encrypted((unsigned long)addr, 1 << order))
+		return;
+	free_pages((unsigned long)addr, order);
+}
+
+static struct gen_pool *itt_pool;
+
+static void *itt_alloc_pool(int node, int size)
+{
+	unsigned long addr;
+	struct page *page;
+
+	if (size >= PAGE_SIZE) {
+		page = its_alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, get_order(size));
+
+		return page ? page_address(page) : NULL;
+	}
+
+	do {
+		addr = gen_pool_alloc(itt_pool, size);
+		if (addr)
+			break;
+
+		page = its_alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+		if (!page)
+			break;
+
+		gen_pool_add(itt_pool, (unsigned long)page_address(page), PAGE_SIZE, node);
+	} while (!addr);
+
+	return (void *)addr;
+}
+
+static void itt_free_pool(void *addr, int size)
+{
+	if (!addr)
+		return;
+
+	if (size >= PAGE_SIZE) {
+		its_free_pages(addr, get_order(size));
+		return;
+	}
+
+	gen_pool_free(itt_pool, (unsigned long)addr, size);
+}
+
 /*
  * Skip ITSs that have no vLPIs mapped, unless we're on GICv4.1, as we
  * always have vSGIs mapped.
@@ -620,7 +712,6 @@ static struct its_collection *its_build_mapd_cmd(struct its_node *its,
 	u8 size = ilog2(desc->its_mapd_cmd.dev->nr_ites);
 
 	itt_addr = virt_to_phys(desc->its_mapd_cmd.dev->itt);
-	itt_addr = ALIGN(itt_addr, ITS_ITT_ALIGN);
 
 	its_encode_cmd(cmd, GITS_CMD_MAPD);
 	its_encode_devid(cmd, desc->its_mapd_cmd.dev->device_id);
@@ -796,8 +887,8 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its,
 	its_encode_valid(cmd, desc->its_vmapp_cmd.valid);
 
 	if (!desc->its_vmapp_cmd.valid) {
+		alloc = !atomic_dec_return(&desc->its_vmapp_cmd.vpe->vmapp_count);
 		if (is_v4_1(its)) {
-			alloc = !atomic_dec_return(&desc->its_vmapp_cmd.vpe->vmapp_count);
 			its_encode_alloc(cmd, alloc);
 			/*
 			 * Unmapping a VPE is self-synchronizing on GICv4.1,
@@ -816,13 +907,13 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its,
 	its_encode_vpt_addr(cmd, vpt_addr);
 	its_encode_vpt_size(cmd, LPI_NRBITS - 1);
 
+	alloc = !atomic_fetch_inc(&desc->its_vmapp_cmd.vpe->vmapp_count);
+
 	if (!is_v4_1(its))
 		goto out;
 
 	vconf_addr = virt_to_phys(page_address(desc->its_vmapp_cmd.vpe->its_vm->vprop_page));
 
-	alloc = !atomic_fetch_inc(&desc->its_vmapp_cmd.vpe->vmapp_count);
-
 	its_encode_alloc(cmd, alloc);
 
 	/*
@@ -1317,7 +1408,6 @@ static void its_send_vmovp(struct its_vpe *vpe)
 {
 	struct its_cmd_desc desc = {};
 	struct its_node *its;
-	unsigned long flags;
 	int col_id = vpe->col_idx;
 
 	desc.its_vmovp_cmd.vpe = vpe;
@@ -1337,8 +1427,7 @@ static void its_send_vmovp(struct its_vpe *vpe)
 	 *
 	 * Wall <-- Head.
 	 */
-	raw_spin_lock_irqsave(&vmovp_lock, flags);
-
+	guard(raw_spinlock)(&vmovp_lock);
 	desc.its_vmovp_cmd.seq_num = vmovp_seq_num++;
 	desc.its_vmovp_cmd.its_list = get_its_list(vpe->its_vm);
 
@@ -1353,8 +1442,6 @@ static void its_send_vmovp(struct its_vpe *vpe)
 		desc.its_vmovp_cmd.col = &its->collections[col_id];
 		its_send_single_vcommand(its, its_build_vmovp_cmd, &desc);
 	}
-
-	raw_spin_unlock_irqrestore(&vmovp_lock, flags);
 }
 
 static void its_send_vinvall(struct its_node *its, struct its_vpe *vpe)
@@ -1726,17 +1813,10 @@ static u64 its_irq_get_msi_base(struct its_device *its_dev)
 static void its_irq_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	struct its_node *its;
-	u64 addr;
-
-	its = its_dev->its;
-	addr = its->get_msi_base(its_dev);
-
-	msg->address_lo		= lower_32_bits(addr);
-	msg->address_hi		= upper_32_bits(addr);
-	msg->data		= its_get_event_id(d);
 
-	iommu_dma_compose_msi_msg(irq_data_get_msi_desc(d), msg);
+	msg->data = its_get_event_id(d);
+	msi_msg_set_addr(irq_data_get_msi_desc(d), msg,
+			 its_dev->its->get_msi_base(its_dev));
 }
 
 static int its_irq_set_irqchip_state(struct irq_data *d,
@@ -1791,12 +1871,10 @@ static bool gic_requires_eager_mapping(void)
 
 static void its_map_vm(struct its_node *its, struct its_vm *vm)
 {
-	unsigned long flags;
-
 	if (gic_requires_eager_mapping())
 		return;
 
-	raw_spin_lock_irqsave(&vmovp_lock, flags);
+	guard(raw_spinlock_irqsave)(&vm->vmapp_lock);
 
 	/*
 	 * If the VM wasn't mapped yet, iterate over the vpes and get
@@ -1809,65 +1887,53 @@ static void its_map_vm(struct its_node *its, struct its_vm *vm)
 
 		for (i = 0; i < vm->nr_vpes; i++) {
 			struct its_vpe *vpe = vm->vpes[i];
-			struct irq_data *d = irq_get_irq_data(vpe->irq);
 
-			/* Map the VPE to the first possible CPU */
-			vpe->col_idx = cpumask_first(cpu_online_mask);
-			its_send_vmapp(its, vpe, true);
+			scoped_guard(raw_spinlock, &vpe->vpe_lock)
+				its_send_vmapp(its, vpe, true);
+
 			its_send_vinvall(its, vpe);
-			irq_data_update_effective_affinity(d, cpumask_of(vpe->col_idx));
 		}
 	}
-
-	raw_spin_unlock_irqrestore(&vmovp_lock, flags);
 }
 
 static void its_unmap_vm(struct its_node *its, struct its_vm *vm)
 {
-	unsigned long flags;
-
 	/* Not using the ITS list? Everything is always mapped. */
 	if (gic_requires_eager_mapping())
 		return;
 
-	raw_spin_lock_irqsave(&vmovp_lock, flags);
+	guard(raw_spinlock_irqsave)(&vm->vmapp_lock);
 
 	if (!--vm->vlpi_count[its->list_nr]) {
 		int i;
 
-		for (i = 0; i < vm->nr_vpes; i++)
+		for (i = 0; i < vm->nr_vpes; i++) {
+			guard(raw_spinlock)(&vm->vpes[i]->vpe_lock);
 			its_send_vmapp(its, vm->vpes[i], false);
+		}
 	}
-
-	raw_spin_unlock_irqrestore(&vmovp_lock, flags);
 }
 
 static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
-	int ret = 0;
 
 	if (!info->map)
 		return -EINVAL;
 
-	raw_spin_lock(&its_dev->event_map.vlpi_lock);
-
 	if (!its_dev->event_map.vm) {
 		struct its_vlpi_map *maps;
 
 		maps = kcalloc(its_dev->event_map.nr_lpis, sizeof(*maps),
 			       GFP_ATOMIC);
-		if (!maps) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!maps)
+			return -ENOMEM;
 
 		its_dev->event_map.vm = info->map->vm;
 		its_dev->event_map.vlpi_maps = maps;
 	} else if (its_dev->event_map.vm != info->map->vm) {
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	/* Get our private copy of the mapping information */
@@ -1899,46 +1965,32 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info)
 		its_dev->event_map.nr_vlpis++;
 	}
 
-out:
-	raw_spin_unlock(&its_dev->event_map.vlpi_lock);
-	return ret;
+	return 0;
 }
 
 static int its_vlpi_get(struct irq_data *d, struct its_cmd_info *info)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_vlpi_map *map;
-	int ret = 0;
-
-	raw_spin_lock(&its_dev->event_map.vlpi_lock);
 
 	map = get_vlpi_map(d);
 
-	if (!its_dev->event_map.vm || !map) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!its_dev->event_map.vm || !map)
+		return -EINVAL;
 
 	/* Copy our mapping information to the incoming request */
 	*info->map = *map;
 
-out:
-	raw_spin_unlock(&its_dev->event_map.vlpi_lock);
-	return ret;
+	return 0;
 }
 
 static int its_vlpi_unmap(struct irq_data *d)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
-	int ret = 0;
-
-	raw_spin_lock(&its_dev->event_map.vlpi_lock);
 
-	if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d)) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d))
+		return -EINVAL;
 
 	/* Drop the virtual mapping */
 	its_send_discard(its_dev, event);
@@ -1946,7 +1998,7 @@ static int its_vlpi_unmap(struct irq_data *d)
 	/* and restore the physical one */
 	irqd_clr_forwarded_to_vcpu(d);
 	its_send_mapti(its_dev, d->hwirq, event);
-	lpi_update_config(d, 0xff, (LPI_PROP_DEFAULT_PRIO |
+	lpi_update_config(d, 0xff, (lpi_prop_prio |
 				    LPI_PROP_ENABLED |
 				    LPI_PROP_GROUP1));
 
@@ -1962,9 +2014,7 @@ static int its_vlpi_unmap(struct irq_data *d)
 		kfree(its_dev->event_map.vlpi_maps);
 	}
 
-out:
-	raw_spin_unlock(&its_dev->event_map.vlpi_lock);
-	return ret;
+	return 0;
 }
 
 static int its_vlpi_prop_update(struct irq_data *d, struct its_cmd_info *info)
@@ -1992,6 +2042,8 @@ static int its_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu_info)
 	if (!is_v4(its_dev->its))
 		return -EINVAL;
 
+	guard(raw_spinlock)(&its_dev->event_map.vlpi_lock);
+
 	/* Unmap request? */
 	if (!info)
 		return its_vlpi_unmap(d);
@@ -2201,8 +2253,8 @@ static void its_lpi_free(unsigned long *bitmap, u32 base, u32 nr_ids)
 
 static void gic_reset_prop_table(void *va)
 {
-	/* Priority 0xa0, Group-1, disabled */
-	memset(va, LPI_PROP_DEFAULT_PRIO | LPI_PROP_GROUP1, LPI_PROPBASE_SZ);
+	/* Regular IRQ priority, Group-1, disabled */
+	memset(va, lpi_prop_prio | LPI_PROP_GROUP1, LPI_PROPBASE_SZ);
 
 	/* Make sure the GIC will observe the written configuration */
 	gic_flush_dcache_to_poc(va, LPI_PROPBASE_SZ);
@@ -2212,7 +2264,8 @@ static struct page *its_allocate_prop_table(gfp_t gfp_flags)
 {
 	struct page *prop_page;
 
-	prop_page = alloc_pages(gfp_flags, get_order(LPI_PROPBASE_SZ));
+	prop_page = its_alloc_pages(gfp_flags,
+				    get_order(LPI_PROPBASE_SZ));
 	if (!prop_page)
 		return NULL;
 
@@ -2223,8 +2276,7 @@ static struct page *its_allocate_prop_table(gfp_t gfp_flags)
 
 static void its_free_prop_table(struct page *prop_page)
 {
-	free_pages((unsigned long)page_address(prop_page),
-		   get_order(LPI_PROPBASE_SZ));
+	its_free_pages(page_address(prop_page), get_order(LPI_PROPBASE_SZ));
 }
 
 static bool gic_check_reserved_range(phys_addr_t addr, unsigned long size)
@@ -2346,7 +2398,7 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
 		order = get_order(GITS_BASER_PAGES_MAX * psz);
 	}
 
-	page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO, order);
+	page = its_alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO, order);
 	if (!page)
 		return -ENOMEM;
 
@@ -2359,7 +2411,7 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser,
 		/* 52bit PA is supported only when PageSize=64K */
 		if (psz != SZ_64K) {
 			pr_err("ITS: no 52bit PA support when psz=%d\n", psz);
-			free_pages((unsigned long)base, order);
+			its_free_pages(base, order);
 			return -ENXIO;
 		}
 
@@ -2415,7 +2467,7 @@ retry_baser:
 		pr_err("ITS@%pa: %s doesn't stick: %llx %llx\n",
 		       &its->phys_base, its_base_type_string[type],
 		       val, tmp);
-		free_pages((unsigned long)base, order);
+		its_free_pages(base, order);
 		return -ENXIO;
 	}
 
@@ -2554,8 +2606,7 @@ static void its_free_tables(struct its_node *its)
 
 	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
 		if (its->tables[i].base) {
-			free_pages((unsigned long)its->tables[i].base,
-				   its->tables[i].order);
+			its_free_pages(its->tables[i].base, its->tables[i].order);
 			its->tables[i].base = NULL;
 		}
 	}
@@ -2729,6 +2780,7 @@ static u64 inherit_vpe_l1_table_from_its(void)
 		}
 		val |= FIELD_PREP(GICR_VPROPBASER_4_1_SIZE, GITS_BASER_NR_PAGES(baser) - 1);
 
+		*this_cpu_ptr(&local_4_1_its) = its;
 		return val;
 	}
 
@@ -2766,6 +2818,7 @@ static u64 inherit_vpe_l1_table_from_rd(cpumask_t **mask)
 		gic_data_rdist()->vpe_l1_base = gic_data_rdist_cpu(cpu)->vpe_l1_base;
 		*mask = gic_data_rdist_cpu(cpu)->vpe_table_mask;
 
+		*this_cpu_ptr(&local_4_1_its) = *per_cpu_ptr(&local_4_1_its, cpu);
 		return val;
 	}
 
@@ -2821,7 +2874,7 @@ static bool allocate_vpe_l2_table(int cpu, u32 id)
 
 	/* Allocate memory for 2nd level table */
 	if (!table[idx]) {
-		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(psz));
+		page = its_alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(psz));
 		if (!page)
 			return false;
 
@@ -2940,7 +2993,7 @@ static int allocate_vpe_l1_table(void)
 
 	pr_debug("np = %d, npg = %lld, psz = %d, epp = %d, esz = %d\n",
 		 np, npg, psz, epp, esz);
-	page = alloc_pages(GFP_ATOMIC | __GFP_ZERO, get_order(np * PAGE_SIZE));
+	page = its_alloc_pages(GFP_ATOMIC | __GFP_ZERO, get_order(np * PAGE_SIZE));
 	if (!page)
 		return -ENOMEM;
 
@@ -2986,8 +3039,7 @@ static struct page *its_allocate_pending_table(gfp_t gfp_flags)
 {
 	struct page *pend_page;
 
-	pend_page = alloc_pages(gfp_flags | __GFP_ZERO,
-				get_order(LPI_PENDBASE_SZ));
+	pend_page = its_alloc_pages(gfp_flags | __GFP_ZERO, get_order(LPI_PENDBASE_SZ));
 	if (!pend_page)
 		return NULL;
 
@@ -2999,7 +3051,7 @@ static struct page *its_allocate_pending_table(gfp_t gfp_flags)
 
 static void its_free_pending_table(struct page *pt)
 {
-	free_pages((unsigned long)page_address(pt), get_order(LPI_PENDBASE_SZ));
+	its_free_pages(page_address(pt), get_order(LPI_PENDBASE_SZ));
 }
 
 /*
@@ -3334,8 +3386,8 @@ static bool its_alloc_table_entry(struct its_node *its,
 
 	/* Allocate memory for 2nd level table */
 	if (!table[idx]) {
-		page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
-					get_order(baser->psz));
+		page = its_alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
+					    get_order(baser->psz));
 		if (!page)
 			return false;
 
@@ -3430,15 +3482,18 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	if (WARN_ON(!is_power_of_2(nvecs)))
 		nvecs = roundup_pow_of_two(nvecs);
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	/*
 	 * Even if the device wants a single LPI, the ITT must be
 	 * sized as a power of two (and you need at least one bit...).
 	 */
 	nr_ites = max(2, nvecs);
 	sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1);
-	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
-	itt = kzalloc_node(sz, GFP_KERNEL, its->numa_node);
+	sz = max(sz, ITS_ITT_ALIGN);
+
+	itt = itt_alloc_pool(its->numa_node, sz);
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+
 	if (alloc_lpis) {
 		lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
 		if (lpi_map)
@@ -3450,9 +3505,9 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 		lpi_base = 0;
 	}
 
-	if (!dev || !itt ||  !col_map || (!lpi_map && alloc_lpis)) {
+	if (!dev || !itt || !col_map || (!lpi_map && alloc_lpis)) {
 		kfree(dev);
-		kfree(itt);
+		itt_free_pool(itt, sz);
 		bitmap_free(lpi_map);
 		kfree(col_map);
 		return NULL;
@@ -3462,6 +3517,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 
 	dev->its = its;
 	dev->itt = itt;
+	dev->itt_sz = sz;
 	dev->nr_ites = nr_ites;
 	dev->event_map.lpi_map = lpi_map;
 	dev->event_map.col_map = col_map;
@@ -3489,7 +3545,7 @@ static void its_free_device(struct its_device *its_dev)
 	list_del(&its_dev->entry);
 	raw_spin_unlock_irqrestore(&its_dev->its->lock, flags);
 	kfree(its_dev->event_map.col_map);
-	kfree(its_dev->itt);
+	itt_free_pool(its_dev->itt, its_dev->itt_sz);
 	kfree(its_dev);
 }
 
@@ -3568,8 +3624,33 @@ out:
 	return err;
 }
 
+static void its_msi_teardown(struct irq_domain *domain, msi_alloc_info_t *info)
+{
+	struct its_device *its_dev = info->scratchpad[0].ptr;
+
+	guard(mutex)(&its_dev->its->dev_alloc_lock);
+
+	/* If the device is shared, keep everything around */
+	if (its_dev->shared)
+		return;
+
+	/* LPIs should have been already unmapped at this stage */
+	if (WARN_ON_ONCE(!bitmap_empty(its_dev->event_map.lpi_map,
+				       its_dev->event_map.nr_lpis)))
+		return;
+
+	its_lpi_free(its_dev->event_map.lpi_map,
+		     its_dev->event_map.lpi_base,
+		     its_dev->event_map.nr_lpis);
+
+	/* Unmap device/itt, and get rid of the tracking */
+	its_send_mapd(its_dev, 0);
+	its_free_device(its_dev);
+}
+
 static struct msi_domain_ops its_msi_domain_ops = {
 	.msi_prepare	= its_msi_prepare,
+	.msi_teardown	= its_msi_teardown,
 };
 
 static int its_irq_gic_domain_alloc(struct irq_domain *domain,
@@ -3670,7 +3751,6 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 {
 	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	struct its_node *its = its_dev->its;
 	int i;
 
 	bitmap_release_region(its_dev->event_map.lpi_map,
@@ -3684,30 +3764,11 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 		irq_domain_reset_irq_data(data);
 	}
 
-	mutex_lock(&its->dev_alloc_lock);
-
-	/*
-	 * If all interrupts have been freed, start mopping the
-	 * floor. This is conditioned on the device not being shared.
-	 */
-	if (!its_dev->shared &&
-	    bitmap_empty(its_dev->event_map.lpi_map,
-			 its_dev->event_map.nr_lpis)) {
-		its_lpi_free(its_dev->event_map.lpi_map,
-			     its_dev->event_map.lpi_base,
-			     its_dev->event_map.nr_lpis);
-
-		/* Unmap device/itt */
-		its_send_mapd(its_dev, 0);
-		its_free_device(its_dev);
-	}
-
-	mutex_unlock(&its->dev_alloc_lock);
-
 	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
 }
 
 static const struct irq_domain_ops its_domain_ops = {
+	.select			= msi_lib_irq_domain_select,
 	.alloc			= its_irq_domain_alloc,
 	.free			= its_irq_domain_free,
 	.activate		= its_irq_domain_activate,
@@ -3827,14 +3888,46 @@ static void its_vpe_db_proxy_move(struct its_vpe *vpe, int from, int to)
 	raw_spin_unlock_irqrestore(&vpe_proxy.lock, flags);
 }
 
+static void its_vpe_4_1_invall_locked(int cpu, struct its_vpe *vpe)
+{
+	void __iomem *rdbase;
+	u64 val;
+
+	val  = GICR_INVALLR_V;
+	val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id);
+
+	guard(raw_spinlock)(&gic_data_rdist_cpu(cpu)->rd_lock);
+	rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
+	gic_write_lpir(val, rdbase + GICR_INVALLR);
+	wait_for_syncr(rdbase);
+}
+
 static int its_vpe_set_affinity(struct irq_data *d,
 				const struct cpumask *mask_val,
 				bool force)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
-	struct cpumask common, *table_mask;
+	unsigned int from, cpu = nr_cpu_ids;
+	struct cpumask *table_mask;
+	struct its_node *its;
 	unsigned long flags;
-	int from, cpu;
+
+	/*
+	 * Check if we're racing against a VPE being destroyed, for
+	 * which we don't want to allow a VMOVP.
+	 */
+	if (!atomic_read(&vpe->vmapp_count)) {
+		if (gic_requires_eager_mapping())
+			return -EINVAL;
+
+		/*
+		 * If we lazily map the VPEs, this isn't an error and
+		 * we can exit cleanly.
+		 */
+		cpu = cpumask_first(mask_val);
+		irq_data_update_effective_affinity(d, cpumask_of(cpu));
+		return IRQ_SET_MASK_OK_DONE;
+	}
 
 	/*
 	 * Changing affinity is mega expensive, so let's be as lazy as
@@ -3848,7 +3941,14 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	 * protect us, and that we must ensure nobody samples vpe->col_idx
 	 * during the update, hence the lock below which must also be
 	 * taken on any vLPI handling path that evaluates vpe->col_idx.
+	 *
+	 * Finally, we must protect ourselves against concurrent updates of
+	 * the mapping state on this VM should the ITS list be in use (see
+	 * the shortcut in its_send_vmovp() otherewise).
 	 */
+	if (its_list_map)
+		raw_spin_lock(&vpe->its_vm->vmapp_lock);
+
 	from = vpe_to_cpuid_lock(vpe, &flags);
 	table_mask = gic_data_rdist_cpu(from)->vpe_table_mask;
 
@@ -3856,10 +3956,15 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	 * If we are offered another CPU in the same GICv4.1 ITS
 	 * affinity, pick this one. Otherwise, any CPU will do.
 	 */
-	if (table_mask && cpumask_and(&common, mask_val, table_mask))
-		cpu = cpumask_test_cpu(from, &common) ? from : cpumask_first(&common);
-	else
+	if (table_mask)
+		cpu = cpumask_any_and(mask_val, table_mask);
+	if (cpu < nr_cpu_ids) {
+		if (cpumask_test_cpu(from, mask_val) &&
+		    cpumask_test_cpu(from, table_mask))
+			cpu = from;
+	} else {
 		cpu = cpumask_first(mask_val);
+	}
 
 	if (from == cpu)
 		goto out;
@@ -3867,12 +3972,20 @@ static int its_vpe_set_affinity(struct irq_data *d,
 	vpe->col_idx = cpu;
 
 	its_send_vmovp(vpe);
+
+	its = find_4_1_its();
+	if (its && its->flags & ITS_FLAGS_WORKAROUND_HISILICON_162100801)
+		its_vpe_4_1_invall_locked(cpu, vpe);
+
 	its_vpe_db_proxy_move(vpe, from, cpu);
 
 out:
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 	vpe_to_cpuid_unlock(vpe, flags);
 
+	if (its_list_map)
+		raw_spin_unlock(&vpe->its_vm->vmapp_lock);
+
 	return IRQ_SET_MASK_OK_DONE;
 }
 
@@ -3941,6 +4054,8 @@ static void its_vpe_invall(struct its_vpe *vpe)
 {
 	struct its_node *its;
 
+	guard(raw_spinlock_irqsave)(&vpe->its_vm->vmapp_lock);
+
 	list_for_each_entry(its, &its_nodes, entry) {
 		if (!is_v4(its))
 			continue;
@@ -4073,7 +4188,7 @@ static struct irq_chip its_vpe_irq_chip = {
 
 static struct its_node *find_4_1_its(void)
 {
-	static struct its_node *its = NULL;
+	struct its_node *its = *this_cpu_ptr(&local_4_1_its);
 
 	if (!its) {
 		list_for_each_entry(its, &its_nodes, entry) {
@@ -4169,22 +4284,12 @@ static void its_vpe_4_1_deschedule(struct its_vpe *vpe,
 
 static void its_vpe_4_1_invall(struct its_vpe *vpe)
 {
-	void __iomem *rdbase;
 	unsigned long flags;
-	u64 val;
 	int cpu;
 
-	val  = GICR_INVALLR_V;
-	val |= FIELD_PREP(GICR_INVALLR_VPEID, vpe->vpe_id);
-
 	/* Target the redistributor this vPE is currently known on */
 	cpu = vpe_to_cpuid_lock(vpe, &flags);
-	raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
-	rdbase = per_cpu_ptr(gic_rdists->rdist, cpu)->rd_base;
-	gic_write_lpir(val, rdbase + GICR_INVALLR);
-
-	wait_for_syncr(rdbase);
-	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	its_vpe_4_1_invall_locked(cpu, vpe);
 	vpe_to_cpuid_unlock(vpe, flags);
 }
 
@@ -4476,9 +4581,8 @@ static int its_vpe_init(struct its_vpe *vpe)
 	raw_spin_lock_init(&vpe->vpe_lock);
 	vpe->vpe_id = vpe_id;
 	vpe->vpt_page = vpt_page;
-	if (gic_rdists->has_rvpeid)
-		atomic_set(&vpe->vmapp_count, 0);
-	else
+	atomic_set(&vpe->vmapp_count, 0);
+	if (!gic_rdists->has_rvpeid)
 		vpe->vpe_proxy_event = -1;
 
 	return 0;
@@ -4527,8 +4631,6 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 	struct page *vprop_page;
 	int base, nr_ids, i, err = 0;
 
-	BUG_ON(!vm);
-
 	bitmap = its_lpi_alloc(roundup_pow_of_two(nr_irqs), &base, &nr_ids);
 	if (!bitmap)
 		return -ENOMEM;
@@ -4548,6 +4650,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 	vm->db_lpi_base = base;
 	vm->nr_db_lpis = nr_ids;
 	vm->vprop_page = vprop_page;
+	raw_spin_lock_init(&vm->vmapp_lock);
 
 	if (gic_rdists->has_rvpeid)
 		irqchip = &its_vpe_4_1_irq_chip;
@@ -4579,6 +4682,10 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain,
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
 	struct its_node *its;
 
+	/* Map the VPE to the first possible CPU */
+	vpe->col_idx = cpumask_first(cpu_online_mask);
+	irq_data_update_effective_affinity(d, cpumask_of(vpe->col_idx));
+
 	/*
 	 * If we use the list map, we issue VMAPP on demand... Unless
 	 * we're on a GICv4.1 and we eagerly map the VPE on all ITSs
@@ -4587,9 +4694,6 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain,
 	if (!gic_requires_eager_mapping())
 		return 0;
 
-	/* Map the VPE to the first possible CPU */
-	vpe->col_idx = cpumask_first(cpu_online_mask);
-
 	list_for_each_entry(its, &its_nodes, entry) {
 		if (!is_v4(its))
 			continue;
@@ -4598,8 +4702,6 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain,
 		its_send_vinvall(its, vpe);
 	}
 
-	irq_data_update_effective_affinity(d, cpumask_of(vpe->col_idx));
-
 	return 0;
 }
 
@@ -4780,6 +4882,25 @@ static bool its_set_non_coherent(void *data)
 	return true;
 }
 
+static bool __maybe_unused its_enable_quirk_hip09_162100801(void *data)
+{
+	struct its_node *its = data;
+
+	its->flags |= ITS_FLAGS_WORKAROUND_HISILICON_162100801;
+	return true;
+}
+
+static bool __maybe_unused its_enable_rk3568002(void *data)
+{
+	if (!of_machine_is_compatible("rockchip,rk3566") &&
+	    !of_machine_is_compatible("rockchip,rk3568"))
+		return false;
+
+	gfp_flags_quirk |= GFP_DMA32;
+
+	return true;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
 	{
@@ -4826,6 +4947,14 @@ static const struct gic_quirk its_quirks[] = {
 		.init	= its_enable_quirk_hip07_161600802,
 	},
 #endif
+#ifdef CONFIG_HISILICON_ERRATUM_162100801
+	{
+		.desc	= "ITS: Hip09 erratum 162100801",
+		.iidr	= 0x00051736,
+		.mask	= 0xffffffff,
+		.init	= its_enable_quirk_hip09_162100801,
+	},
+#endif
 #ifdef CONFIG_ROCKCHIP_ERRATUM_3588001
 	{
 		.desc   = "ITS: Rockchip erratum RK3588001",
@@ -4839,6 +4968,14 @@ static const struct gic_quirk its_quirks[] = {
 		.property = "dma-noncoherent",
 		.init   = its_set_non_coherent,
 	},
+#ifdef CONFIG_ROCKCHIP_ERRATUM_3568002
+	{
+		.desc   = "ITS: Rockchip erratum RK3568002",
+		.iidr   = 0x0201743b,
+		.mask   = 0xffffffff,
+		.init   = its_enable_rk3568002,
+	},
+#endif
 	{
 	}
 };
@@ -4989,7 +5126,12 @@ out_unmap:
 
 static int its_init_domain(struct its_node *its)
 {
-	struct irq_domain *inner_domain;
+	struct irq_domain_info dom_info = {
+		.fwnode		= its->fwnode_handle,
+		.ops		= &its_domain_ops,
+		.domain_flags	= its->msi_domain_flags,
+		.parent		= its_parent,
+	};
 	struct msi_domain_info *info;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
@@ -4998,18 +5140,12 @@ static int its_init_domain(struct its_node *its)
 
 	info->ops = &its_msi_domain_ops;
 	info->data = its;
+	dom_info.host_data = info;
 
-	inner_domain = irq_domain_create_hierarchy(its_parent,
-						   its->msi_domain_flags, 0,
-						   its->fwnode_handle, &its_domain_ops,
-						   info);
-	if (!inner_domain) {
+	if (!msi_create_parent_irq_domain(&dom_info, &gic_v3_its_msi_parent_ops)) {
 		kfree(info);
 		return -ENOMEM;
 	}
-
-	irq_domain_update_bus_token(inner_domain, DOMAIN_BUS_NEXUS);
-
 	return 0;
 }
 
@@ -5128,8 +5264,9 @@ static int __init its_probe_one(struct its_node *its)
 		}
 	}
 
-	page = alloc_pages_node(its->numa_node, GFP_KERNEL | __GFP_ZERO,
-				get_order(ITS_CMD_QUEUE_SZ));
+	page = its_alloc_pages_node(its->numa_node,
+				    GFP_KERNEL | __GFP_ZERO,
+				    get_order(ITS_CMD_QUEUE_SZ));
 	if (!page) {
 		err = -ENOMEM;
 		goto out_unmap_sgir;
@@ -5193,7 +5330,7 @@ static int __init its_probe_one(struct its_node *its)
 out_free_tables:
 	its_free_tables(its);
 out_free_cmd:
-	free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
+	its_free_pages(its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
 out_unmap_sgir:
 	if (its->sgir_base)
 		iounmap(its->sgir_base);
@@ -5385,7 +5522,7 @@ static struct its_node __init *its_node_init(struct resource *res,
 	its->base = its_base;
 	its->phys_base = res->start;
 	its->get_msi_base = its_irq_get_msi_base;
-	its->msi_domain_flags = IRQ_DOMAIN_FLAG_ISOLATED_MSI;
+	its->msi_domain_flags = IRQ_DOMAIN_FLAG_ISOLATED_MSI | IRQ_DOMAIN_FLAG_MSI_IMMUTABLE;
 
 	its->numa_node = numa_node;
 	its->fwnode_handle = handle;
@@ -5597,6 +5734,10 @@ static int __init gic_acpi_parse_madt_its(union acpi_subtable_headers *header,
 		goto node_err;
 	}
 
+	if (acpi_get_madt_revision() >= 7 &&
+	    (its_entry->flags & ACPI_MADT_ITS_NON_COHERENT))
+		its->flags |= ITS_FLAGS_FORCE_NON_SHAREABLE;
+
 	err = its_probe_one(its);
 	if (!err)
 		return 0;
@@ -5667,7 +5808,7 @@ int __init its_lpi_memreserve_init(void)
 }
 
 int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
-		    struct irq_domain *parent_domain)
+		    struct irq_domain *parent_domain, u8 irq_prio)
 {
 	struct device_node *of_node;
 	struct its_node *its;
@@ -5675,8 +5816,13 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists,
 	bool has_v4_1 = false;
 	int err;
 
+	itt_pool = gen_pool_create(get_order(ITS_ITT_ALIGN), -1);
+	if (!itt_pool)
+		return -ENOMEM;
+
 	gic_rdists = rdists;
 
+	lpi_prop_prio = irq_prio;
 	its_parent = parent_domain;
 	of_node = to_of_node(handle);
 	if (of_node)